{3, MVT::v32i8, 14}, // (load 96i8 and) deinterleave into 3 x 32i8
{3, MVT::v2i16, 5}, // (load 6i16 and) deinterleave into 3 x 2i16
+ {3, MVT::v4i16, 7}, // (load 12i16 and) deinterleave into 3 x 4i16
{3, MVT::v8i32, 17}, // (load 24i32 and) deinterleave into 3 x 8i32
{3, MVT::v32i8, 13}, // interleave 3 x 32i8 into 96i8 (and store)
{3, MVT::v2i16, 4}, // interleave 3 x 2i16 into 6i16 (and store)
+ {3, MVT::v4i16, 6}, // interleave 3 x 4i16 into 12i16 (and store)
{4, MVT::v2i8, 4}, // interleave 4 x 2i8 into 8i8 (and store)
{4, MVT::v4i8, 4}, // interleave 4 x 4i8 into 16i8 (and store)
;
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX2: LV: Found an estimated cost of 8 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2
-; AVX2: LV: Found an estimated cost of 31 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2
+; AVX2: LV: Found an estimated cost of 10 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX2: LV: Found an estimated cost of 58 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX2: LV: Found an estimated cost of 129 for VF 16 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX2: LV: Found an estimated cost of 258 for VF 32 For instruction: %v0 = load i16, i16* %in0, align 2
;
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i16 %v2, i16* %out2, align 2
; AVX2: LV: Found an estimated cost of 7 for VF 2 For instruction: store i16 %v2, i16* %out2, align 2
-; AVX2: LV: Found an estimated cost of 30 for VF 4 For instruction: store i16 %v2, i16* %out2, align 2
+; AVX2: LV: Found an estimated cost of 9 for VF 4 For instruction: store i16 %v2, i16* %out2, align 2
; AVX2: LV: Found an estimated cost of 53 for VF 8 For instruction: store i16 %v2, i16* %out2, align 2
; AVX2: LV: Found an estimated cost of 129 for VF 16 For instruction: store i16 %v2, i16* %out2, align 2
; AVX2: LV: Found an estimated cost of 258 for VF 32 For instruction: store i16 %v2, i16* %out2, align 2